Abstract

A common problem with lectures and colleges is that students have difficulty choosing a course due to the large number of choices, or the student credits are limited due to poor course results. We hope that by designing this value prediction application and course recommendations, we will help students get the best course recommendations according to their abilities and grades. The program uses the C45 algorithm to display the selection of courses with the lowest score, and the scores generated by collaborative filtering calculations are advanced by determining the value of similarity between students and predicting grades. The system will identify each course with the highest average score / highest pass rate and it will be used as a student course recommendation. Test results show that the accuracy in determining a student's recommended course using the C45 algorithm is 70%, and the calculation error in determining a student's value prediction is 40-56%.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call